Triple

T6262097
Position Surface form Disambiguated ID Type / Status
Subject Antonov An-32 E140323 entity
Predicate variant P4680 FINISHED
Object An‑32B E140323 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: An‑32B | Statement: [Antonov An-32, variant, An‑32B]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: An‑32B
Context triple: [Antonov An-32, variant, An‑32B]
  • A. Antonov An-32 chosen
    The Antonov An-32 is a twin-engine turboprop military transport aircraft designed for hot-and-high operations, widely used for tactical airlift and cargo missions.
  • B. Antonov An-72
    The Antonov An-72 is a Soviet-designed short takeoff and landing (STOL) transport aircraft known for its distinctive overwing engine configuration and use in both military and civilian roles.
  • C. Antonov An-26
    The Antonov An-26 is a twin-engine Soviet-era turboprop transport aircraft widely used for military and cargo operations around the world.
  • D. Antonov An-12
    The Antonov An-12 is a Soviet-era four-engine turboprop military transport aircraft widely used for cargo and troop transport by numerous air forces and civilian operators around the world.
  • E. FA-50
    The FA-50 is a South Korean light combat and trainer aircraft developed from the T-50 Golden Eagle, used for both advanced pilot training and multirole combat missions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c008c95c5c819084bd3dd56133d84d completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06386a7b48190b032edd12078c5bc completed March 22, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5192b99d4819083ab6e6f2092547b completed March 26, 2026, 11:31 a.m.
Created at: March 22, 2026, 4:25 p.m.